Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1641 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2698. Min Act: -0.0001

Data Index: 1618199 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2548. Min Act: -0.0001

Data Index: 1536895 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2548. Min Act: -0.0001

Data Index: 1516295 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2198. Min Act: -0.0001

Data Index: 1546670 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2431. Min Act: -0.0001

Data Index: 1526603 (Python Code)

Max Activating Token Index: 66

Text #5

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2424. Min Act: -0.0001

Data Index: 1633057 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2358. Min Act: -0.0001

Data Index: 1467330 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.3042. Min Act: -0.0001

Data Index: 1642142 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2195. Min Act: -0.0001

Data Index: 1368596 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2246. Min Act: -0.0001

Data Index: 1410728 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2233. Min Act: -0.0001

Data Index: 1410215 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1810. Min Act: -0.0001

Data Index: 1619460 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2070. Min Act: -0.0001

Data Index: 1420943 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1673. Min Act: -0.0001

Data Index: 1599451 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1680. Min Act: -0.0001

Data Index: 1633491 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1681. Min Act: -0.0001

Data Index: 1617923 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2003. Min Act: -0.0001

Data Index: 1430454 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.2409. Min Act: -0.0001

Data Index: 1381531 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1894. Min Act: -0.0001

Data Index: 1392268 (Python Code)

Max Activating Token Index: 119

Text #19

Max Range: 1.3042. Min Range: -1.3042

Max Act: 1.1909. Min Act: -0.0001

Data Index: 1605852 (Python Code)

Max Activating Token Index: 64